© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 22720
    Prev
    Next
    INDEX
    Explanations

    phrases related to Microsoft’s business practices and privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.30
    1:0.04
    2:0.07
    3:0.06
    4:0.04
    5:0.02
    6:0.10
    7:0.13
    8:0.02
    9:0.05
    10:0.09
    11:0.04
    Negative Logits
     Lancaster
    -4.14
     Wichita
    -3.95
     Tar
    -3.78
    Tar
    -3.71
     Freddy
    -3.67
     Asheville
    -3.65
     Venezuel
    -3.61
     Maduro
    -3.56
     Jagu
    -3.48
     Venezuelan
    -3.38
    POSITIVE LOGITS
     Microsoft
    8.04
    Microsoft
    7.97
     Redmond
    7.07
     Cortana
    6.81
     Kinect
    6.31
     Xbox
    6.30
     Azure
    6.23
    microsoft
    6.19
    Xbox
    6.08
     Windows
    5.83
    Activations Density 0.146%

    No Known Activations